open-llm-leaderboard-old/details_LeroyDyer__Mixtral_AI_Cyber_3.0
收藏数据集概述
该数据集是在对模型 LeroyDyer/Mixtral_AI_Cyber_3.0 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 该数据集包含 63 个配置，每个配置对应一个评估任务。
- 数据集从 1 次运行中创建，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。
- "train" 分片始终指向最新的结果。
- 一个额外的配置 "results" 存储所有运行的聚合结果，用于计算和显示 Open LLM Leaderboard 上的聚合指标。
最新结果
以下是 2024-03-29T20:46:43.223151 运行的最新结果：
python { "all": { "acc": 0.6197012396861927, "acc_stderr": 0.03276132338243605, "acc_norm": 0.6229738232191697, "acc_norm_stderr": 0.033427474229373366, "mc1": 0.40758873929008566, "mc1_stderr": 0.017201949234553107, "mc2": 0.5821381038382072, "mc2_stderr": 0.015259206479110166 }, "harness|arc:challenge|25": { "acc": 0.591296928327645, "acc_stderr": 0.014365750345427, "acc_norm": 0.6245733788395904, "acc_norm_stderr": 0.01415063143511173 }, "harness|hellaswag|10": { "acc": 0.6584345747858992, "acc_stderr": 0.004732654295724446, "acc_norm": 0.8401712806213901, "acc_norm_stderr": 0.003656982165386171 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5481481481481482, "acc_stderr": 0.04299268905480864, "acc_norm": 0.5481481481481482, "acc_norm_stderr": 0.04299268905480864 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6513157894736842, "acc_stderr": 0.038781398887976104, "acc_norm": 0.6513157894736842, "acc_norm_stderr": 0.038781398887976104 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7094339622641509, "acc_stderr": 0.02794321998933713, "acc_norm": 0.7094339622641509, "acc_norm_stderr": 0.02794321998933713 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.03745554791462457, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.03745554791462457 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.630057803468208, "acc_stderr": 0.0368122963339432, "acc_norm": 0.630057803468208, "acc_norm_stderr": 0.0368122963339432 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909284, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5659574468085107, "acc_stderr": 0.03240038086792747, "acc_norm": 0.5659574468085107, "acc_norm_stderr": 0.03240038086792747 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5586206896551724, "acc_stderr": 0.04137931034482757, "acc_norm": 0.5586206896551724, "acc_norm_stderr": 0.04137931034482757 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3915343915343915, "acc_stderr": 0.025138091388851105, "acc_norm": 0.3915343915343915, "acc_norm_stderr": 0.025138091388851105 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7387096774193549, "acc_stderr": 0.024993053397764815, "acc_norm": 0.7387096774193549, "acc_norm_stderr": 0.024993053397764815 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4630541871921182, "acc_stderr": 0.035083705204426656, "acc_norm": 0.4630541871921182, "acc_norm_stderr": 0.035083705204426656 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.04725815626252609, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252609 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.02860620428922987, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.02860620428922987 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8756476683937824, "acc_stderr": 0.023814477086593556, "acc_norm": 0.8756476683937824, "acc_norm_stderr": 0.023814477086593556 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6641025641025641, "acc_stderr": 0.02394672474156397, "acc_norm": 0.6641025641025641, "acc_norm_stderr": 0.02394672474156397 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.31851851851851853, "acc_stderr": 0.028406533090608452, "acc_norm": 0.31851851851851853, "acc_norm_stderr": 0.028406533090608452 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6848739
